Monitoring data and natural language driven bridge finite element model rapid construction method, system and equipment and storage medium

Abstract

The invention discloses a monitoring data and natural language driven bridge finite element model rapid construction method, system and device and a storage medium, and belongs to the technical field of bridge models.The method comprises the following steps that a bridge initial finite element model is constructed based on Midas Civil NX and a natural language; optimized and corrected bridge finite element model parameters are obtained based on the bridge initial finite element model and the PSO optimization model architecture, the bridge initial finite element model is corrected, and a bridge reference finite element model capable of reflecting the real state of the structure is obtained; and importing the obtained bridge key monitoring data into the bridge reference finite element model in real time, calculating an accurate bridge structure response and verification coefficient, and carrying out rapid verification and visual display on the safety state of the bridge structure. According to the method, efficient construction of the bridge finite element model is achieved, the method is particularly suitable for large-quantity and wide-range bridge groups with similar structural forms, and technical support is provided for scheme design and safety inspection of a bridge monitoring system.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of bridge health monitoring, and particularly relates to a monitoring data and natural language driven bridge finite element model rapid construction method, system, device and storage medium. BACKGROUND

[0002] Driven by a series of policies of the Ministry of Transport, the construction of health monitoring systems for highway and national and provincial highway bridge groups is accelerating in various places. Finite element analysis plays a key role in bridge health monitoring system measurement point layout and early warning value setting. According to article 10.4.6 of the Technical Specification for Highway Bridge Structure Monitoring (JTT1037-2022), a structure finite element model sub-database needs to be constructed and saved in a standard file format, and needs to be regularly modified according to monitoring data and maintenance and repair results.

[0003] However, the current bridge health monitoring technology and finite element model analysis technology are disconnected, and the bridge structure models of most domestic monitoring system platforms are mainly BIM models or VR models, which do not have structure analysis and calculation functions. Both monitoring data analysis and finite element model analysis are for the purpose of structure safety analysis, so it is necessary to integrate the two and break the data island effect to realize monitoring data driven finite element model structure analysis and further improve the timeliness and accuracy of structure analysis.

[0004] The traditional manual finite element modeling process is tedious, and users need to manually input various modeling parameters in the finite element software interface, which is time-consuming, labor-intensive and requires high technical skills. In actual engineering, many bridge monitoring systems (especially lightweight systems) do not perform finite element calculation, but rely on experience to layout measurement points, which brings great uncertainty to the quality control of the monitoring scheme. At present, some scholars have studied bridge finite element modeling, but mainly focus on bridge finite element rapid modeling, and few involve post-processing functions such as automatic execution of calculation, extraction of results and automatic generation of calculation reports.

[0005] In addition, early constructed bridges are inevitably affected by environmental erosion, load action and material aging, etc., resulting in resistance attenuation and damage accumulation, which further threatens their operation safety and applicability. However, the existing models are mostly constructed based on design drawing parameters, which are highly idealized, directly leading to large deviations between the calculation results and the measured values, so it is necessary to modify the initial structure three-dimensional finite element model to more accurately and comprehensively study the stress state of the structure and provide a benchmark model for studying other mechanical properties of the structure. However, the mainstream finite element model modification method generally relies on response surface method to construct a surrogate model (such as a hyper-surface function) to approximate the complex implicit relationship. Such methods not only easily lead to simulation deviation due to overfitting, but also increase the system complexity and computational burden in the process of constructing the surrogate model. SUMMARY

[0006] The present application aims to overcome the deficiencies in the prior art, and provides a monitoring data and natural language driven bridge finite element model rapid construction analysis method, system, device and storage medium, which can directly update the finite element model by combining the PSO optimization model with the Midas API, is high in accuracy and reliability, and improves the modeling efficiency.

[0007] To achieve the above object, the present application is implemented by the following technical scheme: In a first aspect, the present application provides a monitoring data and natural language driven bridge finite element model rapid construction analysis method, comprising the following steps: Step S1: constructing a bridge initial finite element model based on Midas Civil NX and natural language; Step S2: obtaining optimized and corrected bridge finite element model parameters based on the bridge initial finite element model and a PSO optimization model architecture, correcting the bridge initial finite element model, and obtaining a bridge benchmark finite element model that can reflect the true state of the structure; Step S3: importing the obtained bridge key monitoring data into the bridge benchmark finite element model in real time, calculating accurate bridge structure responses and checking coefficients, and performing rapid inspection and visual display of the bridge structure safety state.

[0008] Further, in step S1, a heterogeneous monitoring data adaptation program for bridge wind field, structure temperature, displacement, etc. is developed by using Midas Open API, a data analysis and transmission framework is constructed by using Python language, and precise data docking between the monitoring data and the bridge initial finite element model is performed through the JSON data protocol.

[0009] Further, in step S2, based on the bridge initial finite element model, the bridge main girder first three order natural frequency and key cross section deflection are taken as the target responses, the equivalent elastic modulus, Poisson's ratio, equivalent density, equivalent cross section area, Z-axis equivalent moment of inertia and Y-axis equivalent moment of inertia of the main girder are taken as the basis, and the key to-be-corrected parameters of the bridge model are determined through sensitivity analysis; A static and dynamic force combined objective function is constructed, the finite element calculation of the static and dynamic force combined objective function value is called through the Midas API, the static and dynamic force combined objective function is iteratively calculated based on the PSO model architecture, and the optimized and corrected bridge finite element model parameters are obtained; The optimized and corrected bridge finite element model parameters are updated to the bridge initial finite element model based on Midas to correct the model, and the bridge benchmark finite element model reflecting the true state of the bridge structure is obtained.

[0010] Furthermore, by establishing a connection between Python and MIDAS, standardizing the JSON data-driven modeling process, and combining DeepSeek large-scale model training with automated script generation, intelligent construction of bridge finite element models is achieved. The steps also include: Enter your username and key in MIDAS CIVIL NX to establish a connection between Midas Civil and the server; Use Python to write code to build an HTTP service, input a username and key, and establish a connection between the application and the server; Standardize all kinds of information required for modeling into JSON format, including creating bridge materials, sections, nodes, elements, boundary conditions, different types of loads, load combinations, and structural response extraction; Python reads JSON sequentially and calls the MIDAS API to create objects in batches: first write the nodes, then the elements, then assign material and section values, then apply boundary and load values, and finally submit static and eigenvalue solutions; after the calculation is completed, it reads back the results database and automatically exports the displacement, internal force, and first three frequencies as CSV, completing the pre- and post-processing closed loop; In the parameterized space, the equivalent elastic modulus, density, cross-sectional dimensions and other variables of the main beam are sampled by Latin hypercube sampling. The process is repeated cyclically to obtain several sets of "input parameters - structural response" sample data, which are then uniformly stored in HDF5 files to form a training dataset for the bridge finite element model for deep learning. Supervised learning is performed on the training dataset of the bridge finite element model based on the DeepSeek large model to obtain the mapping relationship between "model parameters and structural response"; Based on the key parameters of the bridge structure of the project, Python modeling scripts and standardized JSON data files are automatically generated for automatic modeling, calculation and response extraction.

[0011] Furthermore, a joint static and dynamic objective function is constructed, which is a scalar function that quantifies the difference between the finite element model response and the measured response. The formula is expressed as: ; Where X = [x1, x2, ..., x] n ] is the parameter vector to be corrected; f si (x) is the i-th simulated natural frequency calculated using the Midas API; f mi It is the measured i-th natural frequency; d mj (X) is the simulated deflection of the j-th critical section under a specified load condition, calculated using the Midas API; d mj This corresponds to the measured deflection; w f wd are weight coefficients to balance the importance of dynamic (frequency) and static (deflection) objectives in the total objective function (can be set according to sensitivity or engineering experience), constraint condition: define the physically feasible range of the parameters x to be corrected (upper and lower limit constraints).

[0012] Further, in step S2, the particle swarm optimization algorithm is used in the PSO optimization model architecture, assuming that in an m-dimensional solution space, there is a population consisting of n particles , the position vector of the i-th particle is , the velocity vector is , the particle searches for a new solution by constantly adjusting its position, calculates its fitness value through the fitness function, and records the optimal solution found and the optimal position experienced by the entire particle swarm ; the particle updates its speed and position through and , which are expressed as: ; ; In the formula: represents the inertia weight, represents the current iteration number; represents the acceleration factor; represents a random number subject to a uniform distribution [0, 1]; is a non-negative constant that adjusts the maximum step size of the flight towards the individual optimal particle and the global optimal particle, respectively; for the inertia weight , a larger inertia weight is conducive to improving the global search capability, and a smaller inertia weight is conducive to improving the local search capability; In order to better balance the global search and local search capabilities in the algorithm, a linearly decreasing inertia weight is used, that is: ; In the formula, represents the maximum inertia weight; represents the minimum inertia weight; represents the maximum iteration number.

[0013] Further, based on the B / S architecture visual model, an interactive analysis platform is built through the Vue.js framework, integrating historical analysis backtracking, structural response visualization and other functional modules; using the D3.js rendering engine, dynamic loading of the structural response cloud chart is realized, and the system reliability is verified based on the actual monitoring data of the project bridge.

[0014] In a second aspect, the present application provides a monitoring data and natural language driven bridge finite element model rapid construction analysis system, characterized in that it comprises the following modules: An initial modeling module is configured to construct an initial bridge finite element model based on Midas Civil NX and natural language; A benchmark modeling module is configured to obtain optimized and corrected bridge finite element model parameters based on the initial bridge finite element model and a PSO optimization model architecture, correct the initial bridge finite element model, and obtain a bridge benchmark finite element model that can reflect the true state of the structure; An inspection visualization module is configured to import real-time bridge key monitoring data into the bridge benchmark finite element model, calculate accurate bridge structure responses and calibration coefficients, and perform rapid inspection and visualization of the safety state of the bridge structure.

[0015] In a third aspect, the present application provides an electronic device, characterized in that it comprises: A processor; A memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the monitoring data and natural language driven bridge finite element model rapid construction method according to any one of the first aspect.

[0016] In a fourth aspect, the present application provides a computer readable storage medium, characterized in that when the instructions in the storage medium are executed by the processor of an electronic device, the electronic device can execute the monitoring data and natural language driven bridge finite element model rapid construction method according to any one of the first aspect.

[0017] Compared with the prior art, the present application has the following beneficial effects: the monitoring data and natural language driven bridge finite element model rapid construction method, system, device and storage medium provided by the present application can directly update the finite element model by combining the PSO optimization model with Midas API; the monitoring data and finite element analysis are fused, and the efficiency is improved through script modeling, pre-processing and post-processing, thereby improving the accuracy and reliability of the model; the problems of traditional manual finite element modeling, such as complicated process, low efficiency, high cost, high requirement for software usage level of users, etc. are solved, and the efficient construction of the bridge finite element model can be realized through natural language input, which is especially suitable for large quantities, similar structure forms and high standardization of expressway and national and provincial highway bridge groups, and provides technical support for bridge monitoring system scheme design and safety inspection. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 The flowchart of the monitoring data and natural language driven bridge finite element model rapid construction method provided by the present application is shown.

[0019] Figure 2 Midas API workflow diagram provided for the embodiment of the application.

[0020] Figure 3 Bridge finite element modeling flowchart provided for the embodiment of the application.

[0021] Figure 4 PSO optimization algorithm flowchart provided for the embodiment of the application. DETAILED DESCRIPTION

[0022] The application will be further described below with reference to the drawings. The following embodiments are only used to more clearly illustrate the technical solutions of the application, and cannot be used to limit the protection scope of the application.

[0023] As Figure 1 shown, the embodiment of the application provides a natural language driven bridge finite element model rapid construction method for monitoring data, comprising the following steps: Step S1: constructing a bridge initial finite element model based on Midas Civil NX and natural language; Step S2: obtaining an optimized and corrected bridge finite element model parameter based on the bridge initial finite element model and the PSO optimization model architecture, correcting the bridge initial finite element model, and obtaining a bridge benchmark finite element model that can reflect the true state of the structure; Step S3: importing the obtained bridge key monitoring data into the bridge benchmark finite element model in real time, calculating accurate bridge structure response and checking coefficient, and performing rapid inspection and visual display of the bridge structure safety state.

[0024] Application Programming Interface (API) as the interaction specification between software systems, acts as the "nerve connector" of the digital world, and its core value lies in realizing function abstraction, resource reuse and ecological expansion through standardized interfaces. Traditional APIs such as operating system interfaces (file management, hardware control) have solved the basic interaction requirements, but are limited by platform binding and protocol fragmentation. With the development of cloud computing and Web technology, RESTful API has become an industry standard for cross-platform integration by virtue of the universality of HTTP protocol, stateless architecture and resource design (such as URL positioning model, HTTP method definition operation). From the interface call of the social media sharing button, real-time weather data aggregation to bank open platform services, all are built on this basis.

[0025] MIDAS innovatively adopts a Web-based API architecture, realizing a triple breakthrough in the interaction paradigm of engineering software: ①In terms of communication protocols, the combination of HTTP and WebSocket replaces traditional in-process calls (DLL / COM), transmits instructions through stateless HTTP to penetrate firewalls, and simultaneously utilizes WebSocket full-duplex communication to push analysis progress; ②In terms of architectural design, finite element models are abstracted as REST resources (such as GET / models / nodes to obtain node sets), and multi-instance routing is achieved through mapi-key, enabling a single server to manage hundreds of engineering instances in parallel; ③In terms of data exchange, JSON format is adopted for extremely lightweight transmission, and its hierarchical structure naturally meets the needs of finite element modeling (node coordinate arrays, material constitutive nested objects), combined with cross-platform zero parsing cost characteristics, forming a complete chain from desktop modeling to cloud computing. Figure 2 As shown in the figure, the workflow is as follows: Step 1: The client obtains a REST API request from the server through HTTP protocol; Step 2: The server retrieves the request and requests node information; Step 3: The product sends node information to the server; Step 4: The server obtains the node information and sends it to the client again.

[0026] In this embodiment, in step S1, Midas Open API is used to develop a heterogeneous monitoring data adaptation program for bridge wind field, structural temperature, displacement, etc. Python language is used to build a data parsing and transmission framework, and JSON data protocol is used for precise data docking between monitoring data and initial finite element model of the bridge.

[0027] In this embodiment, in step S2, based on the initial finite element model of the bridge, the first three natural frequencies of the main girder of the bridge and the deflection of the key section are taken as the target responses, and based on the equivalent elastic modulus, Poisson's ratio, equivalent density, equivalent cross-sectional area, Z-axis equivalent moment of inertia, and Y-axis equivalent moment of inertia of the main girder, the sensitivity analysis is performed to determine the key parameters to be modified of the bridge model. A static-dynamic combined objective function is constructed, the value of the static-dynamic combined objective function is calculated by calling the finite element calculation through Midas API, and the static-dynamic combined objective function is iteratively calculated based on the PSO model architecture to obtain the optimized and corrected bridge finite element model parameters. The optimized and corrected bridge finite element model parameters are updated to the initial finite element model of the bridge based on Midas to modify the model, and the bridge benchmark finite element model reflecting the true state of the bridge structure is obtained.

[0028] The traditional manual finite element modeling process is tedious, requiring users to manually input various modeling parameters in the finite element software interface, which is inefficient. Midas API technology uses JSON (JavaScript Object Notation) natural language as a data format to build a bridge finite element modeling method, completely changing the bridge finite element software interaction mode.

[0029] In this embodiment, a connection is established between Python and MIDAS, a standardized JSON data-driven modeling process is used, and a DeepSeek large model is trained and an automatic script is generated to realize intelligent construction of a bridge finite element model. The steps further include: Enter the username and secret key in MIDAS CIVIL NX to establish a connection between Midas Civil and the server; Use Python to write code, build an HTTP service, enter the username and secret key, and realize the connection between the application and the server; Standardize various types of information required for modeling into JSON format, including creating bridge materials, cross sections, nodes, units, boundary conditions, different types of loads, load combinations, and structure response extraction; Python reads JSON in sequence, calls MIDAS API to create objects in batches: first write nodes, then write units, then assign materials and cross sections, then apply boundary conditions and loads, and finally submit static and eigenvalue solutions; After calculation, read the result database, automatically export displacement, internal force, and the first three order frequencies as CSV, and complete the pre-processing and post-processing closed loop; In the parametric space, perform Latin hypercube sampling on variables such as the equivalent elastic modulus, density, and cross-sectional size of the main girder, and perform cyclic execution to obtain a number of "input parameters-structure response" sample data, which are uniformly stored in an HDF5 file to form a bridge finite element model training dataset for deep learning; Based on the DeepSeek large model, supervised learning is performed on the bridge finite element model training dataset to obtain the mapping relationship between "model parameters-structure response"; Based on the key parameters of the bridge structure of the project, Python modeling scripts and standardized JSON data files are automatically generated for automatic modeling, calculation, and response extraction.

[0030] In this embodiment, the code is run to parse the JSON data using a third-party JSON library in Python. Then, using the MIDAS API functions, commands are sent to the server, the server retrieves the request, and the request information is sent to the Midas Civil finite element software, which automatically performs finite element pre-processing and post-processing operations such as creating a new project, defining materials and sections, establishing nodes and elements, inputting boundary conditions, inputting loads, load combinations, structure response extraction, etc.

[0031] In this embodiment, the load input includes three parts: one part is the design load, one part is the binary text in the bridge monitoring system database, and the other part is the manually specified load. For binary text, the structure temperature, wind speed, and other action binary texts from the bridge monitoring system InfluxDB database are converted into JSON format load data; for manually specified load, it is edited directly according to the JSON format; for design load, it is directly input according to the design load level.

[0032] The conversion of binary text to JSON is as follows: ① Data parsing: obtain binary data from InfluxDB and parse binary data according to predefined data structure (such as sensor ID, timestamp, temperature, wind speed, etc.); ② Data conversion: convert the parsed data into a Python dictionary structure according to the load input format of MIDAS; ③ JSON serialization: use the json library of Python to serialize the converted data structure into a JSON string.

[0033] In this embodiment, sensitivity analysis can study how changes in risk factors qualitatively and quantitatively affect the structure response of the forward model, which is a necessary step for finite element model correction. The single-factor sensitivity analysis method assumes that each influencing factor is independent, and by controlling the variable, it fixes other risk factors and changes the value of the target factor one by one to calculate its model output value. Then, according to the change law of the output value with the target factor level value, the sensitivity of the target factor is analyzed.

[0034] In this embodiment, a static-dynamic combined objective function is constructed, which is a scalar function that quantifies the difference between the finite element model response and the measured response, and the formula is as follows: ; where X = [x1, x2…x n ] is the vector of parameters to be corrected; f si (x) is the i-th order modal frequency calculated using Midas API; f mi is the measured i-th order natural frequency; d mj(X) is the simulated deflection of the jth key section under the specified load case calculated by Midas API; d mj is the corresponding measured deflection; w f , w d is the weight coefficient for balancing the importance of dynamic (frequency) and static (deflection) targets in the total objective function (which can be set according to sensitivity or engineering experience), constraint condition: define the physically feasible range of the parameter x to be corrected (upper and lower limit constraints).

[0035] In this embodiment, in step S2, a particle swarm optimization algorithm is used in the PSO optimization model architecture, assuming that in an m-dimensional solution space, there is a population consisting of n particles , the position vector of the ith particle is , the velocity vector is , the particle searches for a new solution by constantly adjusting its position, calculates its fitness value through the fitness function, and records the optimal solution searched and the optimal position experienced by the entire particle swarm ; the particle updates its velocity and position through and , which are expressed as: ; ; In the formula: represents the inertia weight, represents the current iteration number; represents the acceleration factor; represents a random number subject to a uniform distribution [0, 1]; is a non-negative constant that respectively adjusts the maximum step size of flying towards the individual optimal particle and the global optimal particle; for the inertia weight , a larger inertia weight is conducive to improving the global search ability, and a smaller inertia weight is conducive to improving the local search ability.

[0036] In order to better balance the global search and local search capabilities in the algorithm, a linearly decreasing inertia weight is used, that is: ; In the formula, represents the maximum inertia weight; represents the minimum inertia weight; represents the maximum iteration number.

[0037] In the embodiment, based on the B / S architecture visual model, an interactive analysis platform is built through a Vue.js framework, and functional modules such as historical analysis backtracking and structural response visualization are integrated; a D3.js rendering engine is adopted to realize dynamic loading of a structural response cloud chart, and the system reliability is verified based on actual monitoring data of a project bridge.

[0038] In some embodiments, the present application provides a monitoring data and natural language driven bridge finite element model rapid construction system, characterized in that it comprises the following modules: An initial modeling module is configured to construct a bridge initial finite element model based on Midas Civil NX and natural language; A benchmark modeling module is configured to obtain optimized and corrected bridge finite element model parameters based on the bridge initial finite element model and a PSO optimization model architecture, correct the bridge initial finite element model, and obtain a bridge benchmark finite element model that can reflect the true state of the structure; An inspection visualization module is configured to import real-time bridge key monitoring data into the bridge benchmark finite element model, calculate accurate bridge structural responses and calibration coefficients, and perform rapid inspection and visualization display of the bridge structural safety state.

[0039] In some embodiments, the present application provides an electronic device, characterized in that it comprises: A processor; A memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the monitoring data and natural language driven bridge finite element model rapid construction method according to any one of the first aspect.

[0040] In some embodiments, the present application provides a computer readable storage medium, characterized in that when the instructions in the storage medium are executed by the processor of the electronic device, the electronic device can execute the monitoring data and natural language driven bridge finite element model rapid construction method according to any one of the first aspect.

[0041] The above only describes the preferred embodiments of the present application, and it should be noted that for ordinary skilled persons in the technical field, several improvements and modifications can be made without departing from the technical principles of the present application, and these improvements and modifications should also be considered as the protection scope of the present application.

Claims

1. A method for rapid construction of bridge finite element models driven by monitoring data and natural language, characterized in that, Includes the following steps: Step S1: Construct the initial finite element model of the bridge based on Midas Civil NX and natural language processing; Step S2: Based on the initial finite element model of the bridge and the PSO optimized model architecture, obtain the optimized and corrected bridge finite element model parameters, correct the initial finite element model of the bridge, and obtain a bridge reference finite element model that can reflect the true state of the structure. Step S3: Import the acquired key bridge monitoring data into the bridge reference finite element model in real time, calculate the accurate bridge structural response and verification coefficients, and perform rapid inspection and visualization of the bridge structural safety status.

2. The method for rapid construction of bridge finite element models driven by monitoring data and natural language as described in claim 1, characterized in that, In step S1, the Midas Open API is used to develop an adaptation program for heterogeneous monitoring data such as bridge wind field, structural temperature, and displacement. The Python language is used to build a data parsing and transmission framework, and the monitoring data and the initial finite element model of the bridge are accurately connected through the JSON data protocol.

3. The method for rapid construction of bridge finite element models driven by monitoring data and natural language as described in claim 1, characterized in that, In step S2, based on the initial finite element model of the bridge, the first three natural frequencies of the main beam and the deflection of the key sections are taken as the target responses. Based on the equivalent elastic modulus, Poisson's ratio, equivalent density, equivalent cross-sectional area, equivalent moment of inertia of the Z-axis and equivalent moment of inertia of the main beam, the key parameters to be corrected in the bridge model are identified through sensitivity analysis. A combined static and dynamic objective function is constructed, and the value of the combined static and dynamic objective function is calculated by calling the finite element method through the Midas API. The combined static and dynamic objective function is iteratively calculated based on the PSO model architecture to obtain the optimized and corrected bridge finite element model parameters. The optimized and corrected bridge finite element model parameters are updated and applied to the initial finite element model of the bridge based on Midas for model correction, resulting in a bridge reference finite element model that reflects the true state of the bridge structure.

4. The method for rapid construction of bridge finite element models driven by monitoring data and natural language as described in claim 1, characterized in that, By establishing a connection between Python and MIDAS, standardizing the JSON data-driven modeling process, and combining DeepSeek large-scale model training with automated script generation, intelligent construction of bridge finite element models is achieved. The steps also include: Enter your username and key in MIDAS CIVIL NX to establish a connection between Midas Civil and the server; Use Python to write code to build an HTTP service, input a username and key, and establish a connection between the application and the server; Standardize all kinds of information required for modeling into JSON format, including creating bridge materials, sections, nodes, elements, boundary conditions, different types of loads, load combinations, and structural response extraction; Python reads JSON sequentially and calls the MIDAS API to create objects in batches: first write the nodes, then the elements, then assign material and section values, then apply boundary and load values, and finally submit static and eigenvalue solutions; after the calculation is completed, it reads back the results database and automatically exports the displacement, internal force, and first three frequencies as CSV, completing the pre- and post-processing closed loop; In the parameterized space, the equivalent elastic modulus, density, cross-sectional dimensions and other variables of the main beam are sampled by Latin hypercube sampling. The process is repeated cyclically to obtain several sets of "input parameters - structural response" sample data, which are then uniformly stored in HDF5 files to form a training dataset for the bridge finite element model for deep learning. Supervised learning is performed on the training dataset of the bridge finite element model based on the DeepSeek large model to obtain the mapping relationship between "model parameters and structural response"; Based on the key parameters of the bridge structure of the project, Python modeling scripts and standardized JSON data files are automatically generated for automatic modeling, calculation and response extraction.

5. The method for rapid construction of bridge finite element models driven by monitoring data and natural language as described in claim 1, characterized in that, A joint static and dynamic objective function is constructed, which is a scalar function that quantifies the difference between the finite element model response and the measured response. The formula is as follows: ； Where X = [x1, x2, ..., x] n ] is the parameter vector to be corrected; f si (x) is the i-th simulated natural frequency calculated using the Midas API; f mi It is the measured i-th natural frequency; d mj (X) is the simulated deflection of the j-th critical section under a specified load condition, calculated using the Midas API; d mj This corresponds to the measured deflection; w f w d It is a weighting coefficient used to balance the importance of dynamic (frequency) and static (deflection) targets in the overall objective function (it can be set according to sensitivity or engineering experience). Constraints: Define the physical feasible range (upper and lower limits) of the parameter x to be corrected.

6. The method for rapid construction of bridge finite element models driven by monitoring data and natural language as described in claim 1, characterized in that, In step S2, the PSO optimization model architecture employs the particle swarm optimization algorithm. Assume there is a population of n particles in the m-dimensional solution space. The position vector of the i-th particle is The velocity vector is Particles search for new solutions by continuously adjusting their positions, calculating their fitness value using a fitness function, and recording the optimal solution found. and the optimal position experienced by the entire particle swarm ; Particles pass through and To update its velocity and position representation as follows: ； ； In the formula: Indicates inertia weight, Indicates the current iteration number; Indicates the acceleration factor; This represents a random number that follows a uniform distribution in the interval [0, 1]. These are non-negative constants, used to adjust the maximum step size for flight towards the individual optimal particle and the global optimal particle, respectively; for inertial weights... Generally speaking, a larger inertia weight is beneficial to improving global search capability, while a smaller inertia weight is beneficial to improving local search capability. To better balance the global and local search capabilities of the algorithm, a linearly decreasing inertia weight is used, i.e.: ； In the formula, This represents the maximum inertial weight; This represents the minimum inertia weight; This indicates the maximum number of iterations.

7. The method for rapid construction of bridge finite element models driven by monitoring data and natural language as described in claim 1, characterized in that, Based on the B / S architecture, a visualization model is built using the Vue.js framework to create an interactive analysis platform that integrates functional modules such as historical analysis backtracking and structural response visualization. The D3.js rendering engine is used to dynamically load the structural response cloud map, and the reliability of the system is verified based on the actual monitoring data of the bridge in the project.

8. A rapid construction and analysis system for bridge finite element models driven by monitoring data and natural language, characterized in that, Includes the following modules: The initial modeling module is used to build the initial finite element model of the bridge based on Midas Civil NX and natural language. The benchmark modeling module is used to obtain optimized and corrected bridge finite element model parameters based on the bridge initial finite element model and PSO optimized model architecture, correct the bridge initial finite element model, and obtain a bridge benchmark finite element model that can reflect the true state of the structure. The inspection visualization module is used to import the acquired key monitoring data of the bridge into the bridge reference finite element model in real time, calculate the accurate bridge structural response and verification coefficients, and perform rapid inspection and visualization of the bridge structural safety status.

9. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the rapid construction method of monitoring data and natural language-driven bridge finite element model as described in any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that, When the instructions in the storage medium are executed by the processor of the electronic device, the electronic device is able to execute the rapid construction method of the bridge finite element model driven by monitoring data as described in any one of claims 1 to 6.

Images